FractalGPT/RuQwen2.5-3B-Instruct-AWQ
Same weights, repacked vs Qwen/Qwen2.5-3B-Instruct-AWQ. Same weights in different files (re-saved, re-sharded or new metadata), plus 1 new tensors.
Tensors changed: MLP 0/324, Attention 0/540, Norms 0/73
Same weights, repacked vs Qwen/Qwen2.5-3B-Instruct-AWQ. Same weights in different files (re-saved, re-sharded or new metadata), plus 1 new tensors.
Tensors changed: MLP 0/324, Attention 0/540, Norms 0/73